© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38972
    Prev
    Next
    INDEX
    Explanations

    no `oficial`/`formal`/`fly`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     नई
    0.69
     NTFS
    0.67
     HTTPS
    0.66
     वैध
    0.66
    č
    0.66
     US
    0.66
     directa
    0.66
     NOAA
    0.64
     हरा
    0.64
     talleres
    0.64
    POSITIVE LOGITS
    to
    0.98
    ва
    0.77
    ेलकम
    0.77
    า
    0.77
    de
    0.75
    があります
    0.75
    した
    0.73
    ができる
    0.72
    لی
    0.71
    ت
    0.70
    Activations Density 0.001%

    No Known Activations